Scorecard MCP logo

Scorecard MCP

Scorecard MCP lets agents manage evaluation projects, testsets, testcases, systems, metrics, runs, records, scores, annotations, and documentation searches.

2 actions Integration catalog
Request access
Connect Scorecard MCP once you're in Boring.
01 · WHAT THE AGENT CAN DO

Actions

Every capability is a discrete, logged action the agent calls by name — scoped to what you authorize and recorded in the run trace.

ExecuteSCORECARD_MCP_EXECUTE
Runs JavaScript code to interact with the Scorecard API. You are a skilled TypeScript programmer writing code to interface with the service. Define an async function named "run" that takes a single parameter of an initialized SDK client and it will be run. For example: ``` async function run(client) { const run = await client.runs.create('314', { metricIds: ['789', '101'], testsetId: '246' }); console.log(run.id); } ``` You will be returned anything that your function returns, plus the results of any console.log statements. Do not add try-catch blocks for single API calls. The tool will handle errors for you. Do not add comments unless necessary for generating better code. Code will run in a container, and cannot interact with the network outside of the given SDK client. Variables will not persist between calls, so make sure to return or log any data you might need later. Remember that you are writing TypeScript code, so you need to be careful with your types. Always type dynamic key-value stores explicitly as Record<string, YourValueType> instead of {}.
Search docsSCORECARD_MCP_SEARCH_DOCS
Search SDK documentation to find methods, parameters, and usage examples for interacting with the API. Use this before writing code when you need to discover the right approach.